dx8152/

Qwen-Image-Edit-2509-Relight

Hi everyone overseas! ModelScope has launched its training service abroad.

My LoRa training is all done using ModelScope. Thanks to the ModelScope team for providing the training infrastructure. Give it a try!

Welcome everyone to use Lora of Qwen-Edit-2509 of Image Fusion, its performance is amazing！

Online running link： https://www.runninghub.ai/post/1983425100517187586?inviteCode=rh-v1331

There are two ways to use it: 1. Use the prompts in the dataset to change the image directly. 2. Use the trigger word: " 重新照明 "。 （For example:重新照明,使用窗帘透光（柔和漫射）的光线对图片进行重新照明） Meaning: Relighting, using the soft, diffuse light from the curtains to relight the image.

（I also uploaded the re-light LoRAs for Kontext downloaded from the Internet. The sources are https://civit.ai/models/1779918 and https://hf.co/dong625/kontext_loras/tree/main ）

Instructions: Download the lora file（Qwen-Edit-Relight.safetensors to the models/loras folder.

You also need this lora and use them together: https://huggingface.co/lightx2v/Qwen-Image-Lightning/tree/main

This is the effect used by Lora:

YouTube：https://youtu.be/GmDZmzoseFk

Blibili：https://www.bilibili.com/video/BV11N4NzBEAy/

For communication/cooperation, you can join the discord group to communicate：https://discord.gg/yVAVa43mWk

If these resources are helpful to you, or if you use them for business purposes, please buy me a coffee. Thank you for supporting original content! PayPal: Daniel8152